# flash-next-seat — Qwen3.8-Flash-Next (abliterated) on fv-ml1 GPU 2, :8022.
# Copy to .env on the host at /opt/docker/compose/flash-next-seat/.env.
#
# This is the INITIAL configuration, stood up 2026-09-13. Values marked FIRST-BOOT
# are deliberately conservative and expected to be revised once the seat has
# reported its own memory budget and been bisected for depth. Do not treat them as
# measured — they are not yet.

# ── Image ───────────────────────────────────────────────────────────────────
# ⚠ MUST contain vLLM #54371 (UVA PLE-offload), merged 2026-09-09T14:32Z.
# Verified by ancestry rather than version string: this commit is +150 / behind_by=0
# from merge commit 3116c5d06bfe76501b3dd6b5434bfc7f3274f5e7. v0.29.0 does NOT
# contain it (cut ~6h before the merge) and neither does any nightly-<sha> tag
# dated 2026-09-09 or earlier — the nightly build runs ~06:16 UTC.
FN_IMAGE=vllm/vllm-openai:nightly-eed1f3d0c6043bd494424a22443ee198dd56f657
API_KEY=replace-me

# ── Placement ───────────────────────────────────────────────────────────────
# GPU 2 was completely idle (2 MiB) before this seat; GPU 3 still is. Every other
# compose GPU pin on fv-ml1 is 0 or 1, so this seat displaced nothing.
FN_GPU_ID=2
FN_PORT=8022
FN_CONTAINER_NAME=vllm-flash-next

# ── Model ───────────────────────────────────────────────────────────────────
# dealignai/Qwen3.8-Flash-Next-ABLITERATED-NVFP4 @ be794b990578ef3031eccf9f28e675a289a09ee9
FN_MODEL=/tank/aimodels/qwen38-flash-next-abliterated-nvfp4
FN_QUANT=modelopt_fp4
FN_SERVED_NAME=qwen3.8-flash-next-uncensored
FN_SERVED_NAME_THINK=qwen3.8-flash-next-uncensored-thinking

# ── The offload ─────────────────────────────────────────────────────────────
# The 51B n-gram table (47.7 GiB FP8) lives in pinned host RAM; the GPU reads rows
# over CUDA UVA. Without this the checkpoint needs ~126 GiB of VRAM and will not
# start on one 96 GiB card. fv-ml1 has 566 GB RAM / ~388 GB available, so the
# host side is not a constraint here — unlike every DGX-Spark report upstream,
# where host and device share one unified pool and "offload" frees nothing.
FN_ENGRAM_CONFIG={"cpu_offload": true}

# ── Memory and context ──────────────────────────────────────────────────────
# FIRST-BOOT. Card is dedicated, so 0.90 (the vLLM recipe's own figure for offload
# configs) is not competing with a neighbour. Expected resident weights ~78 GiB of
# 95.6, leaving ~8-9 GiB for KV + activation inside the 0.90 budget.
# ⚠ NEXT STEP after first boot: read vLLM's budget line and replace this with an
# explicit --kv-cache-memory in BYTES. A ratio sizes the KV calculation but does
# not bound peak activation — that is what bit stacks/mog-sec twice on 2026-09-10.
FN_GPU_MEM_UTIL=0.90

# FIRST-BOOT. 128K, against a 262,144 native ceiling. Raising this is gated on a
# depth bisect with a NON-REPEATING prompt, because two open upstream issues make
# depth the risky axis: #54764 (PLE short-conv prefill pads every request in a
# batch to the batch-max query length) and #54919 (long prefill starving decode
# for 3-7 minutes). See the compose comment.
FN_MAX_MODEL_LEN=131072
FN_MAX_NUM_SEQS=16
FN_MAX_NUM_BATCHED_TOKENS=8192
FN_MAMBA_CACHE_MODE=align

# ── Prefix caching ──────────────────────────────────────────────────────────
# ⚠ THE ROLLBACK LEVER for open #54173 (CUBLAS_STATUS_INTERNAL_ERROR / illegal
# memory access in the GDN path, WITH prefix caching). Set to the empty string to
# disable. Leave FN_MAMBA_CACHE_MODE=align either way — Qwen4Exp raises on "all".
FN_PREFIX_CACHING=--enable-prefix-caching

# ── Vision ──────────────────────────────────────────────────────────────────
# 4194304 px = 2048x2048 -> ~5,125 image tokens. The checkpoint's own preprocessor
# declares 16777216 (4096x4096) -> ~16,384 tokens, which is both wasteful and fatal
# on builds enforcing the image-token count check. Same trap as stacks/mog-sec.
FN_MM_PROCESSOR_KWARGS={"size": {"longest_edge": 4194304, "shortest_edge": 65536}}
FN_LIMIT_MM={"image": 4}

# ── Misc ────────────────────────────────────────────────────────────────────
FN_REASONING_PARSER=qwen3
FN_REASONING_EFFORT=medium
FN_TOOL_CALL_PARSER=qwen3_xml
# Intentionally EMPTY. expandable_segments has corrupted retained tensors on this
# box before (quant playbook §3.10) and has never been tested against a pinned
# host allocation handed to UVA.
FN_ALLOC_CONF=

# ── NOT SET, on purpose ─────────────────────────────────────────────────────
# --speculative-config  : MTP is off. vLLM's own recipe measured it WORSE at every
#                         concurrency on 4xH100 (8-36% less throughput, 32-173%
#                         more latency, ~36% acceptance) and open #55357 reports
#                         episodic 0% acceptance with repetition collapse.
# --kv-cache-dtype fp8  : fp8_e4m3 KV on this model's QSA path is an unmerged RFC
#                         (#54426). Do not copy it over from gen/mog-sec.